ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process

Published in NeurIPS, 2024

George Kiyohiro Nakayama, Mikaela Angelina Uy, Yang You, Ke Li, Leonidas Guibas

arXiv / PDF / project page / BibTeX

Abstract

Neural radiance fields (NeRFs) excel at 3D scene reconstruction but struggle with sparse, unconstrained camera views. ProvNeRF addresses this by modeling per-point provenance as a stochastic process, enabling improved uncertainty estimation, criteria-based view optimization, and enhanced novel view synthesis. Our method, compatible with any pre-trained NeRF, extends IMLE for stochastic processes, leveraging training camera poses to enrich the 3D point information.

BibTeX

@inproceedings{nakayama2024provnerf,
  title     = {ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process},
  author    = {George Kiyohiro Nakayama and Mikaela Angelina Uy and Yang You and Ke Li and Leonidas Guibas},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  year      = {2024},
  eprint    = {2401.08140},
  archivePrefix = {arXiv}
}

Recommended citation: Nakayama, G.K., Uy, M.A., You, Y., Li, K., & Guibas, L. (2024). ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process. NeurIPS 2024.